Play 20
Anomaly Detection
High🔧 Skeleton
Real-time anomaly detection with streaming analysis and AI enrichment.
Events flow through Event Hub, Stream Analytics detects statistical anomalies in real time, GPT-4o enriches alerts with natural language explanations and suggested actions. Cosmos DB stores event history for trend analysis. Azure Functions trigger downstream workflows (PagerDuty, Teams, email).
Architecture Pattern
Streaming anomaly detection, event-driven, AI enrichment, alerting
Azure Services
Event HubStream AnalyticsAzure OpenAI (gpt-4o)Azure FunctionsCosmos DB
DevKit (.github Agentic OS)
- agent.md — root orchestrator with builder→reviewer→tuner handoffs
- 3 agents — Anomaly Builder (gpt-4o), Reviewer (gpt-4o-mini), Tuner (gpt-4o-mini)
- 3 skills — deploy (103 lines), evaluate (106 lines), tune (110 lines)
- 4 prompts — /deploy, /test, /review, /evaluate with agent routing
- .vscode/mcp.json — FrootAI MCP with Log Analytics + OpenAI inputs + envFile
TuneKit (AI Config)
- config/detection.json — detection models, sensitivity, thresholds
- config/alerts.json — alert rules, severity mapping
- config/enrichment.json — AI analysis prompts
Tuning Parameters
Detection thresholdsAlert promptsSensitivity levelsDetection windows
Estimated Cost
Dev/Test
$100–250/mo
Production
$1.2K–4K/mo